Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 653 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6916. Min Act: -0.0000

Data Index: 1738884 (The Pile)

Max Activating Token Index: 412

Text #1

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.4512. Min Act: -0.0000

Data Index: 783916 (The Pile)

Max Activating Token Index: 842

Text #2

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.5565. Min Act: -0.0000

Data Index: 1222065 (The Pile)

Max Activating Token Index: 760

Text #3

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.5088. Min Act: -0.0000

Data Index: 1507342 (The Pile)

Max Activating Token Index: 498

Text #4

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.4528. Min Act: -0.0000

Data Index: 521881 (The Pile)

Max Activating Token Index: 400

Text #5

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.3578. Min Act: 0.0000

Data Index: 1275071 (The Pile)

Max Activating Token Index: 896

Text #6

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.3967. Min Act: -0.0000

Data Index: 1286372 (The Pile)

Max Activating Token Index: 698

Text #7

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.3485. Min Act: -0.0000

Data Index: 466136 (The Pile)

Max Activating Token Index: 473

Text #8

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.3555. Min Act: -0.0000

Data Index: 447731 (The Pile)

Max Activating Token Index: 440

Text #9

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.3189. Min Act: -0.0000

Data Index: 1274055 (The Pile)

Max Activating Token Index: 793

Text #10

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2207. Min Act: -0.0000

Data Index: 1907486 (The Pile)

Max Activating Token Index: 896

Text #11

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2707. Min Act: -0.0000

Data Index: 53417 (The Pile)

Max Activating Token Index: 793

Text #12

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2666. Min Act: -0.0000

Data Index: 728570 (The Pile)

Max Activating Token Index: 947

Text #13

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2361. Min Act: -0.0000

Data Index: 1473976 (The Pile)

Max Activating Token Index: 538

Text #14

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2468. Min Act: -0.0000

Data Index: 203245 (The Pile)

Max Activating Token Index: 1000

Text #15

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2743. Min Act: 0.0000

Data Index: 675796 (The Pile)

Max Activating Token Index: 621

Text #16

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.1959. Min Act: 0.0000

Data Index: 798632 (The Pile)

Max Activating Token Index: 786

Text #17

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2394. Min Act: -0.0000

Data Index: 391782 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2301. Min Act: -0.0000

Data Index: 181161 (The Pile)

Max Activating Token Index: 669

Text #19

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.2647. Min Act: 0.0000

Data Index: 846634 (The Pile)

Max Activating Token Index: 446